keylazy commited on
Commit
fb3f0e7
1 Parent(s): 1a66398

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
6
  ],
7
  "attention_dropout": 0.1,
8
- "dim": 768,
9
  "dropout": 0.1,
10
- "hidden_dim": 3072,
11
  "id2label": {
12
  "0": "text1",
13
  "1": "text2"
@@ -17,17 +17,16 @@
17
  "text1": 0,
18
  "text2": 1
19
  },
20
- "max_position_embeddings": 512,
21
  "model_type": "distilbert",
22
- "n_heads": 12,
23
- "n_layers": 6,
24
  "pad_token_id": 0,
25
  "problem_type": "single_label_classification",
26
  "qa_dropout": 0.1,
27
  "seq_classif_dropout": 0.2,
28
  "sinusoidal_pos_embds": false,
29
- "tie_weights_": true,
30
  "torch_dtype": "float32",
31
  "transformers_version": "4.34.1",
32
- "vocab_size": 30522
33
  }
 
1
  {
2
+ "_name_or_path": "distilbert-base-uncased-ark",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
6
  ],
7
  "attention_dropout": 0.1,
8
+ "dim": 128,
9
  "dropout": 0.1,
10
+ "hidden_dim": 256,
11
  "id2label": {
12
  "0": "text1",
13
  "1": "text2"
 
17
  "text1": 0,
18
  "text2": 1
19
  },
20
+ "max_position_embeddings": 64,
21
  "model_type": "distilbert",
22
+ "n_heads": 4,
23
+ "n_layers": 3,
24
  "pad_token_id": 0,
25
  "problem_type": "single_label_classification",
26
  "qa_dropout": 0.1,
27
  "seq_classif_dropout": 0.2,
28
  "sinusoidal_pos_embds": false,
 
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.34.1",
31
+ "vocab_size": 5000
32
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1af000f301c455329d2a811881b407caec0c1c7c3237360f777a5c52551aaf9
3
- size 267854570
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4254632af5dd0c76c925ab0edbad214bdf1a2300f71384a8ee1f3b90f4c922b8
3
+ size 4269078
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": true
10
  },
11
- "100": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": true
18
  },
19
- "101": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "102": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "103": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
@@ -45,11 +45,15 @@
45
  "cls_token": "[CLS]",
46
  "do_lower_case": true,
47
  "mask_token": "[MASK]",
 
48
  "model_max_length": 512,
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
 
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
  "tokenizer_class": "DistilBertTokenizer",
 
 
54
  "unk_token": "[UNK]"
55
  }
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "1": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "3": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "4": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
45
  "cls_token": "[CLS]",
46
  "do_lower_case": true,
47
  "mask_token": "[MASK]",
48
+ "max_length": 64,
49
  "model_max_length": 512,
50
  "pad_token": "[PAD]",
51
  "sep_token": "[SEP]",
52
+ "stride": 0,
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
  "tokenizer_class": "DistilBertTokenizer",
56
+ "truncation_side": "right",
57
+ "truncation_strategy": "longest_first",
58
  "unk_token": "[UNK]"
59
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e69e379a1ef71471ab5a95c3591f3b18b47f2f91baf26d6f1572cf3add1cdcda
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b6184d1109c40081f6747472ce8e5814090f264a02f06648debb55aed88f89
3
  size 4536
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff